Document Server@UHasselt >
Research >
Research publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1942/731

Title: On a Dynamical Analysis of Reinforcement Learning in Games: Emergence of Occam's Razor
Authors: TUYLS, Karl
Verbeeck, Katja
Maes, Sam
Issue Date: 2003
Publisher: Springer
Abstract: Modeling learning agents in the context of Multi-agent Systems requires an adequate understanding of their dynamic behaviour. Usually, these agents are modeled similar to the different players in a standard game theoretical model. Unfortunately traditional Game Theory is static and limited in its usefelness. Evolutionary Game Theory improves on this by providing a dynamics which describes how strategies evolve over time. In this paper, we discuss three learning models whose dynamics are related to the Replicator Dynamics(RD). We show how a classical Reinforcement Learning(RL) technique, i.e. Q-learning relates to the RD. This allows to better understand the learning process and it allows to determine how complex a RL model should be. More precisely, Occam's Razor applies in the framework of games, i.e. the simplest model (Cross) suffices for learning equilibria. An experimental verification in all three models is presented.
URI: http://hdl.handle.net/1942/731
Link to publication: http://www.springerlink.com/openurl.asp?genre=article&issn=0302-9743&volume=2691&spage=335
ISI #: 000184854600032
ISSN: 0302-9743
Category: A1
Type: Journal Contribution
Appears in Collections: Research publications

Files in This Item:

There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.